I strong downvoted and strong disagree voted. The reason I did both is because I think what you’re describing is a genuinely insane standard to take for liability. Holding organizations liable for any action they take which they do not prove is safe is an absolutely terrible idea. It would either introduce enormous costs for doing anything, or allow anyone to be sued for anything they’ve previously done.
Quintin Pope
Karma: 4,901
I really don’t want to spend even more time arguing over my evolution post, so I’ll just copy over our interactions from the previous times you criticized it, since that seems like context readers may appreciate.
In the comment sections of the original post:
[very long, but mainly about your “many other animals also transmit information via non-genetic means” objection + some other mechanisms you think might have caused human takeoff]
I don’t think this objection matters for the argument I’m making. All the cross-generational information channels you highlight are at rough saturation, so they’re not able to contribute to the cross-generational accumulation of capabilities-promoting information. Thus, the enormous disparity between the brain’s with-lifetime learning versus evolution cannot lead to a multiple OOM faster accumulation of capabilities as compared to evolution.
When non-genetic cross-generational channels are at saturation, the plot of capabilities-related info versus generation count looks like this:
with non-genetic information channels only giving the “All info” line a ~constant advantage over “Genetic info”. Non-genetic channels might be faster than evolution, but because they’re saturated, they only give each generation a fixed advantage over where they’d be with only genetic info. In contrast, once the cultural channel allows for an ever-increasing volume of transmitted information, then the vastly faster rate of within-lifetime learning can start contributing to the slope of the “All info” line, and not just its height.
Thus, humanity’s sharp left turn.
In Twitter comments on Open Philanthropy’s announcement of prize winners:
But what’s the central point, than? Evolution discovered how to avoid the genetic bottleneck myriad times; also discovered potentially unbounded ways how to transmit arbitrary number of bits, like learning-teaching behaviours; except humans, nothing foomed. So the updated story would be more like “some amount of non-genetic/cultural accumulation is clearly convergent and is common, but there is apparently some threshold crossed so far only by humans. Once you cross it you unlock a lot of free energy and the process grows explosively”. (&the cause or size of treshold is unexplained)
(note: this was a reply and part of a slightly longer chain)
Firstly, I disagree with your statement that other species have “potentially unbounded ways how to transmit arbitrary number of bits”. Taken literally, of course there’s no species on earth that can actually transmit an *unlimited* amount of cultural information between generations. However, humans are still a clear and massive outlier in the volume of cultural information we can transmit between generations, which is what allows for our continuously increasing capabilities across time.
Secondly, the main point of my article was not to determine why humans, in particular, are exceptional in this regard. The main point was to connect the rapid increase in human capabilities relative to previous evolution-driven progress rates with the greater optimization power of brains as compared to evolution. Being so much better at transmitting cultural information as compared to other species allowed humans to undergo a “data-driven singularity” relative to evolution. While our individual brains and learning processes might not have changed much between us and ancestral humans, the volume and quality of data available for training future generations did increase massively, since past generations were much better able to distill the results of their lifetime learning into higher-quality data.
This allows for a connection between the factors we’ve identified are important for creating powerful AI systems (data volume, data quality, and effectively applied compute), and the process underlying the human “sharp left turn”. It reframes the mechanisms that drove human progress rates in terms of the quantities and narratives that drive AI progress rates, and allows us to more easily see what implications the latter has for the former.
In particular, this frame suggests that the human “sharp left turn” was driven by the exploitation of a one-time enormous resource inefficiency in the structure of the human, species-level optimization process. And while the current process of AI training is not perfectly efficient, I don’t think it has comparably sized overhangs which can be exploited easily. If true, this would mean human evolutionary history provides little evidence for sudden increases in AI capabilities.
The above is also consistent with rapid civilizational progress depending on many additional factors: it relies on resource overhand being a *necessary* factor, but does not require it to be alone *sufficient* to accelerate human progress. There are doubtless many other factors that are relevant, such as a historical environment favorable to progress, a learning process that sufficiently pays attention to other members of ones species, not being a purely aquatic species, and so on. However, any full explanation of the acceleration in human progress of the form:
“sudden progress happens exactly when (resource overhang) AND (X) AND (Y) AND (NOT Z) AND (W OR P OR NOT R) AND...”
is still going to have the above implications for AI progress rates.There’s also an entire second half to the article, which discusses what human “misalignment” to inclusive genetic fitness (doesn’t) mean for alignment, as well as the prospects for alignment during two specific fast takeoff (but not sharp left turn) scenarios, but that seems secondary to this discussion.
I think this post greatly misunderstands mine.
Firstly, I’d like to address the question of epistemics.
When I said “there’s no reason to reference evolution at all when forecasting AI development rates”, I was referring to two patterns of argument that I think are incorrect: (1) using the human sharp left turn as evidence for an AI sharp left turn, and (2) attempting to “rescue” human evolution as an informative analogy for other aspects of AI development.
(Note: I think Zvi did follow my argument for not drawing inferences about the odds of the sharp left turn specifically. I’m still starting by clarifying pattern 1 in order to set things up to better explain pattern 2.)
Pattern 1: using the human sharp left turn as evidence for an AI sharp left turn.
The original sharp left turn post claims that there are general factors about the structure and dynamics of optimization processes which both caused the evolutionary sharp left turn, and will go on to cause another sharp left turn in AI systems. The entire point of Nate referencing evolution is to provide evidence for these factors.
My counterclaim is that the causal processes responsible for the evolutionary sharp left turn are almost entirely distinct from anything present in AI development, and so the evolutionary outcome is basically irrelevant for thinking about AI.
From my perspective, this is just how normal Bayesian reasoning works. If Nate says:
P(human SLT | general factors that cause SLTs) ~= 1
P(human SLT | NOT general factors that cause SLTs) ~= 0
then observing the human SLT is very strong evidence for there being general factors that cause SLTs in different contexts than evolution.
OTOH, I am saying:
P(human SLT | NOT general factors that cause SLTs) ~= 1
And so observing the human SLT is no evidence for such general factors.
Pattern 2: attempting to “rescue” human evolution as an informative analogy for other aspects of AI development.
When I explain my counterargument to pattern 1 to people in person, they will very often try to “rescue” evolution as a worthwhile analogy for thinking about AI development. E.g., they’ll change the analogy so it’s the programmers who are in a role comparable to evolution, rather than SGD.
I claim that such attempted inferences also fail, for the same reason as argument pattern 1 above fails: the relevant portions of the causal graph driving evolutionary outcomes is extremely different from the causal graph driving AI outcomes, such that it’s not useful to use evolution as evidence to make inferences about nodes in the AI outcomes causal graph. E.g., the causal factors that drive programmers to choose a given optimizer are very different from the factors that cause evolution to “choose” a given optimizer. Similarly, evolution is not a human organization that makes decisions based on causal factors that influence human organizations, so you should look at evolution for evidence of organization-level failures that might promote a sharp left turn in AI.
Making this point was the purpose of the “alien space clowns” / EVO-Inc example. It was intended to provide a concrete example of two superficially similar seeming situations, where actually their causal structures are completely distinct, such that there are no useful updates to make from EVO-Inc’s outcomes to other automakers. When Zvi says:
I would also note that, if you discover (as in Quintin’s example of Evo-inc) that major corporations are going around using landmines as hubcaps, and that they indeed managed to gain dominant car market share and build the world’s most functional cars until recently, that is indeed a valuable piece of information about the world, and whether you should trust corporations or other humans to be able to make good choices, realize obvious dangers and build safe objects in general. Why would you think that such evidence should be ignored?
Zvi is proposing that there are common causal factors that led to the alien clowns producing dangerous cars, and could also play a similar role in causing other automakers to make unsafe vehicles, such that Evo-Inc’s outcomes provide useful updates for predicting other automakers’ outcomes. This is what I’m saying is false about evolution versus AI development.
At this point, I should preempt a potential confusion: it’s not the case that AI development and human evolution share zero causal factors! To give a trivial example, both rely on the same physical laws. What prevents there being useful updates from evolution to AI development is the different structure of the causal graphs. When you update your estimates for the shared factors between the graphs using evidence from evolution, this leads to trivial or obvious implications for AI development, because the shared causal factors play different roles in the two graphs. You can have an entirely “benign” causal graph for AI development, which predicts zero alignment issues for AI development, yet when you build the differently structured causal graph for human evolution, it still predicts the same sharp left turn, despite some of the causal factors being shared between the graphs.
This is why inferences from evolutionary outcomes to AI development don’t work. Propagating belief updates through the evolution graph doesn’t change any of the common variables away from settings which are benign in the AI development graph, since those settings already predict a sharp left turn when they’re used in the evolution graph.
Concrete example 1: We know from AI development that having a more powerful optimizer, running for more steps, leads to more progress. Applying this causal factor to the AI development graph basically predicts “scaling laws will continue”, which is just a continuation of the current trajectory. Applying the same factor to the evolution graph, combined with the evolution-specific fact of cultural transmission enabling a (relatively) sudden unleashing of ~9 OOM more effectively leveraged optimization power in a very short period of time, predicts an extremely sharp increase in the rate of progress.
Concrete example 2: One general hypothesis you could have about RL agents is “RL agents just do what they’re trained to do, without any weirdness”. (To be clear, I’m not endorsing this hypothesis. I think it’s much closer to being true than most on LW, but still false.) In the context of AI development, this has pretty benign implications. In the context of evolution, due to the bi-level nature of its optimization process and the different data that different generations are “trained” on, this causal factor in the evolution graph predicts significant divergence between the behaviors of ancestral and modern humans.
Zvi says this is an uncommon standard of epistemics, for there to be no useful inferences from one set of observations (evolutionary outcomes) to another (AI outcomes). I completely disagree. For the vast majority of possible pairs of observations, there are not useful inferences to draw. The pattern of dust specks on my pillow is not a useful reference point for making inferences about the state of the North Korean nuclear weapons program. The relationship between AI development and human evolution is not exceptional in this regard.
Secondly, I’d like to address a common pattern in a lot of Zvi’s criticisms.
My post has a unifying argumentative structure that Zvi seems to almost completely miss. This leads to a very annoying dynamic where:
My post makes a claim / argument that serves a very specific role in the context of the larger structure.
Zvi misses that context, and interprets the claim / argument as making some broader claim about alignment in general.
Zvi complains that I’m over-claiming, being too general, or should split the post along the separate claims Zvi (falsely) believes I’m making.
The unifying argumentative structure of my post is as follows:
Evolution’s sharp left turn happened for evolution-specific reasons
Describes the causal structure of evolution’s sharp left turn.
Don’t misgeneralize from evolution to AI
Argues you shouldn’t generalize between things with very different causal structures.
Fast takeoff is still possible
Clarifies that I am not arguing against fast takeoff, and that fast takeoff can happen without a sharp left turn.
Proposes two AI-specific causal mechanisms that could cause a fast takeoff.
Discusses why it’s alignment relevant if fast takeoff happens because of either of the two mechanisms previously mentioned.
Will alignment generalize across sudden capabilities jumps?
Human “misalignment” with inclusive genetic fitness provides no evidence for AI misalignment
Somewhat awkwardly shoehorns in the argument that evolution also provides no evidence for inner alignment failures in general.
Capabilities jumps due to AI driving AI capabilities research
Argues that this specific fast takeoff mechanism will not itself cause a sharp left turn / alignment failure
Capabilities jumps due to AI iteratively refining its training data
Argues that this specific fast takeoff mechanism will not itself cause a sharp left turn / alignment failure
Having outlined my argumentative structure, I’ll highlight some examples where Zvi’s criticisms fall into the previously mentioned dynamic.
1:
[Zvi] He then goes on to make another very broad claim.
[Zvi quoting me] > In order to experience a sharp left turn that arose due to the same mechanistic reasons as the sharp left turn of human evolution, an AI developer would have to:
[I list some ways one could produce an ML training process that’s actually similar to human evolution in the relevant sense that would lead to an evolution-like sharp left turn at some point]
[Zvi criticizes the above list on the grounds that inner misalignment could occur under a much broader range of circumstances than I describe]
(I added the bolding)
The issue here is that the list in question is specifically for sharp left turns that arise “due to the same mechanistic reasons as the sharp left turn of human evolution”, as I very specifically said in my original post. I’m not talking about inner alignment in general. I’m not even talking about sharp left turn threat scenarios in general! I’m talking very specifically about how the current AI paradigm would have to change before it had a mechanistic structure sufficiently similar to human evolution that I think a sharp left turn would occur “due to the same mechanistic reasons as the sharp left turn of human evolution”.
2:
As a general note, these sections seem mostly to be making a general alignment is easy, alignment-by-default claim, rather than being about what evolution offers evidence for, and I would have liked to see them presented as a distinct post given how big and central and complex and disputed is the claim here.
That is emphatically not what those sections are arguing for. The purpose of these sections is to describe two non-sharp left turn causing mechanisms for fast takeoff, in order to better illustrate that fast takeoff != sharp left turn. Each section specifically focuses on a particular mechanism of fast takeoff, and argues that said mechanism will not, in and of itself, lead to misalignment. You can still believe a fast takeoff driven by that mechanism will lead to misalignment for other reasons (e.g., a causal graph that looks like: “(fast takeoff mechanism) → (capabilities) → (something else) → (misalignment)”), if, say, you think there’s another causal mechanism driving misalignment, such that the fast takeoff mechanism’s only contribution to misalignment was to advance capabilities in a manner that failed to address that other mechanism.
These sections are not arguing about the ease of alignment in general, but about the consequence of one specific process.
3:
The next section seems to argue that because alignment techniques work on a variety of existing training regimes all of similar capabilities level, we should expect alignment techniques to extend to future systems with greater capabilities.
That is, even more emphatically, not what that specific section is arguing for. This section focuses specifically on the “AIs do AI capabilities research” mechanism of fast takeoff, and argues that it will not itself cause misalignment. Its purpose is specific to the context in which I use it: to address the causal influence of (AIs do capabilities research) directly to (misalignment), not to argue about the odds of misalignment in general.
Further, the argument that section made wasn’t:
because alignment techniques work on a variety of existing training regimes all of similar capabilities level, we should expect alignment techniques to extend to future systems
It was:
alignment techniques already generalize across human contributions to AI capability research. Let’s consider eight specific alignment techniques:
[list of alignment techniques]
and eleven recent capabilities advances:
[list of capabilities techniques]
I don’t expect catastrophic interference between any pair of these alignment techniques and capabilities advances.
And so, if you think AIs doing capabilities will be like humans doing capabilities research, but faster, then there will be a bunch of capabilities and alignment techniques, and the question is how much the capabilities techniques will interfere with the alignment techniques. Based on current data, the interference seems small and manageable. This is the trend being projected forwards, the lack of empirical interference between current capabilities and alignment (despite, as I note in my post, current capabilities techniques putting ~zero effort into not interfering with alignment techniques, an obviously dumb oversight which we haven’t corrected because it turns out we don’t even need to do so).
Once again, I emphasize that this is not a general argument about alignment, which can be detached from the rest of the post. It’s extremely specific to the mechanism for fast takeoff being analyzed, which is only being analyzed to further explore the connection between fast takeoff mechanisms and the odds of a sharp left turn.
4:
He closes by arguing that iteratively improving training data also exhibits important differences from cultural development, sufficient to ignore the evolutionary evidence as not meaningful in this context. I do not agree. Even if I did agree, I do not see how that would justify his broader optimism expressed here:
This part is a separate analysis of a different fast takeoff causal mechanism, arguing that it will not, itself cause misalignment either. Its purpose and structure mirrors that of the argument I clarified above, but focused on a different mechanism. It’s not a continuation of a previous (non-existent) “alignment is easy in general” argument.
Thirdly, I’d like to make some random additional commentary.
I would argue that ‘AIs contribute to AI capabilities research’ is highly analogous to ‘humans contribute to figuring out how to train other humans.’ And that ‘AIs seeking out new training data’ is highly analogous to ‘humans creating bespoke training data to use to train other people especially their children via culture’ which are exactly the mechanisms Quintin is describing humans as using to make a sharp left turn.
The degree of similarity is arguable. I think, and said in the original article, that similarity is low for the first mechanism and moderate for the second.
However, the appropriate way to estimate the odds of a given fast takeoff mechanism leading to AI misalignment is not to estimate the similarity between that mechanism and what happened during human evolution, then assign misalignment risk to the mechanism in proportion to the estimated similarity. Rather, the correct approach is to build detailed causal models of how both human evolution and AI development work, propagate the evidence from human evolutionary outcomes back through your human evolution causal model to update relevant latent variables in that causal model, transfer those updates to any of the AI development causal model’s latent variables which are also in the human evolution causal model, and finally estimate the new misalignment risk implied by the updated variables of the AI development model.
I discussed this in more detail in the first part of my comment, but whenever I do this, I find that the transfer from (observations of evolutionary outcomes) to (predictions about AI development) are pretty trivial or obvious, leading to such groundbreaking insights as:
More optimization power leads to faster progress
Human level general intelligence is possible
Neural architecture search is a bad thing to spend most of your compute on
Retraining a fresh instance of your architecture from scratch on different data will lead to different behavior
That seems like a sharp enough left turn to me.
A sharp left turn is more than just a fast takeoff. It’s the combined sudden increase in AI generality and breaking of previously existing alignment properties.
...humans being clearly misaligned with genetic fitness is not evidence that we should expect such alignment issues in AIs. His argument (without diving into his earlier linked post) seems to be that humans are fresh instances trained on new data, so of course we expect different alignment and different behavior.
But if you believe that, you are saying that humans are fresh versions of the system. You are entirely throwing out from your definition of ‘the system’ all of the outer alignment and evolutionary data, entirely, saying it does not matter, that only the inner optimizer matters. In which case, yes, that does fully explain the differences. But the parallel here does not seem heartening. It is saying that the outcome is entirely dependent on the metaphorical inner optimizer, and what the system is aligned to will depend heavily on the details of the training data it is fed and the conditions under which it is trained, and what capabilities it has during that process, and so on. Then we will train new more capable systems in new ways with new data using new techniques, in an iterated way, in similar fashion. How should this make us feel better about the situation and its likely results?
I find this perspective baffling. Where else do the alignment properties of a system derive from? If you have a causal structure like
(programmers) → (training data, training conditions, learning dynamics, etc) → (alignment properties)
then setting the value of the middle node will of course screen off the causal influence of the (programmers) node.
A possible clarification: in the context of my post when discussing evolution, “inner optimizer” means the brain’s “base” optimization process, not the human values / intelligence that arises from that process. The mechanistically most similar thing in AI development to that meaning of the word “inner optimizer” is the “base” training process: the combination of training data, base optimizer, training process, architecture, etc. It doesn’t mean the cognitive system that arises as a consequence of running that training process.
Consider the counterfactual. If we had not seen a sharp left turn in evolution, civilization had taken millions of years to develop to this point with gradual steady capability gains, and we saw humans exhibiting strong conscious optimization mostly for their genetic fitness, it would seem crazy not to change our beliefs at all about what is to come compared to what we do observe. Thus, evidence.
I think Zvi is describing a ~impossible world. I think this world would basically break ~all my models on how optimizing processes gain capabilities. My new odds of an AI sharp left turn would depend on the new models I made in this world, which in turn would depend on unspecified details of how human civilization’s / AI progress happens in this world.
I would also note that Quintin in my experience often cites parallels between humans and AIs as a reason to expect good outcomes from AI due to convergent outcomes, in circumstances where it would be easy to find many similar distinctions between the two cases. Here, although I disagree with his conclusions, I agree with him that the human case provides important evidence.
Once again, it’s not the degree of similarity that determines what inferences are appropriate. It’s the relative structure of the two causal graphs for the processes in question. The graphs for the human brain and current AI systems are obviously not the same, but they share latent variables that serve similar roles in determining outcomes, in a way that the bi-level structure of evolution’s causal graph largely prevents. E.g., Steven Byrnes has a whole sequence which discusses the brain’s learning process, and while there are lots of differences between the brain and current AI designs, there are also shared building blocks whose behaviors are driven by common causal factors. The key difference with evolution is that, once one updates the shared variables from looking at human brain outcomes and applies those updates to the AI development graph, there are non-trivial / obvious implications. Thus, one can draw relevant inferences by observing human outcomes.
Concrete example 1: brains use a local, non-gradient based optimization process to minimize predictive error, so there exists some non-SGD update rules that are competitive with SGD (on brainlike architectures, at least).
Concrete example 2: brains don’t require GPT-4 level volumes of training data, so there exist architectures with vastly more data-friendly scaling laws than GPT-4′s scaling.
In the generally strong comments to OP, Steven Byrnes notes that current LLM systems are incapable of autonomous learning, versus humans and AlphaZero which are, and that we should expect this ability in future LLMs at some point. Constitutional AI is not mentioned, but so far it has only been useful for alignment rather than capabilities, and Quintin suggests autonomous learning mostly relies upon a gap between generation and discernment in favor of discernment being easier. I think this is an important point, while noting that what matters is ability to discern between usefully outputs at all, rather than it being easier, which is an area where I keep trying to put my finger on writing down the key dynamics and so far falling short.
What I specifically said was:
Autonomous learning basically requires there to be a generator-discriminator gap in the domain in question, i.e., that the agent trying to improve its capabilities in said domain has to be better able to tell the difference between its own good and bad outputs.
I realize this is accidentally sounds like it’s saying two things at once (that autonomous learning relies on the generator-discriminator gap of the domain, and then that it relies on the gap for the specific agent (or system in general)). To clarify, I think it’s the agent’s capabilities that matter, that the domain determines how likely the agent is to have a persistent gap between generation and discrimination, and I don’t think the (basic) dynamics are too difficult to write down.
You start with a model M and initial data distribution D. You train M on D such that M is now a model of D. You can now sample from M, and those samples will (roughly) have whatever range of capabilities were to be found in D.
Now, suppose you have some classifier, C, which is able to usefully distinguish samples from M on the basis of that sample’s specific level of capabilities. Note that C doesn’t have to just be an ML model. It could be any process at all, including “ask a human”, “interpret the sample as a computer program trying to solve some problem, run the program, and score the output”, etc.
Having C allows you to sample from a version of M’s output distribution that has been “updated” on C, by continuously sampling from M until a sample scores well on C. This lets you create a new dataset D’, which you can then train M’ on to produce a model of the updated distribution.
So long as C is able to provide classification scores which actually reflect a higher level of capabilities among the samples from M / M’ / M″ / etc, you can repeat this process to continually crank up the capabilities. If your classifier C was some finetune of M, then you can even create a new C’ off of M’, and potentially improve the classifier along with your generator. In most domains though, classifier scores will eventually begin to diverge from the qualities that actually make an output good / high capability, and you’ll eventually stop benefiting from this process.
This process goes further in domains where it’s easier to distinguish generations by their quality. Chess / other board games are extreme outliers in this regard, since you can always tell which of two players actually won the game. Thus, the game rules act as a (pairwise) infallible classifier of relative capabilities. There’s some slight complexity around that last point, since a given trajectory could falsely appear good by beating an even worse / non-representative policy, but modern self-play approaches address such issues by testing model versions against a variety of opponents (mostly past versions of themselves) to ensure continual real progress. Pure math proofs is another similarly skewed domain, where building a robust verifier (i.e., a classifier) of proofs is easy. That’s why Steven was able to use it as a valid example of where self-play gets you very far.
Most important real world domains do not work like this. E.g., if there were a robust, easy-to-query process that could classify which of two scientific theories / engineering designs / military strategies / etc was actually better, the world would look extremely different.
There are other issues I have with this post, but my reply is already longer than the entire original post, so I’ll stop here, rather than, say, adding an entire additional section on my models of takeoff speed for AIs versus evolution (which I’ll admit probably should have another post to go with it).
Addressing this objection is why I emphasized the relatively low information content that architecture / optimizers provide for minds, as compared to training data. We’ve gotten very far in instantiating human-like behaviors by training networks on human-like data. I’m saying the primacy of data for determining minds means you can get surprisingly close in mindspace, as compared to if you thought architecture / optimizer / etc were the most important.
Obviously, there are still huge gaps between the sorts of data that an LLM is trained on versus the implicit loss functions human brains actually minimize, so it’s kind of surprising we’ve even gotten this far. The implication I’m pointing to is that it’s feasible to get really close to human minds along important dimensions related to values and behaviors, even without replicating all the quirks of human mental architecture.
I believe the human visual cortex is actually the more relevant comparison point for estimating the level of danger we face due to mesaoptimization. Its training process is more similar to the self-supervised / offline way in which we train (base) LLMs. In contrast, ‘most abstract / “psychological”’ are more entangled in future decision-making. They’re more “online”, with greater ability to influence their future training data.
I think it’s not too controversial that online learning processes can have self-reinforcing loops in them. Crucially however, such loops rely on being able to influence the externally visible data collection process, rather than being invisibly baked into the prior. They are thus much more amenable to being addressed with scalable oversight approaches.
I’m guessing you misunderstand what I meant when I referred to “the human learning process” as the thing that was a ~ 1 billion X stronger optimizer than evolution and responsible for the human SLT. I wasn’t referring to human intelligence or what we might call human “in-context learning”. I was referring to the human brain’s update rules / optimizer: i.e., whatever quasi-Hebbian process the brain uses to minimize sensory prediction error, maximize reward, and whatever else factors into the human “base objective”. I was not referring to the intelligences that the human base optimizers build over a lifetime.
If instead of reward circuitry inducing human values, evolution directly selected over policies, I’d expect similar inner alignment failures.
I very strongly disagree with this. “Evolution directly selecting over policies” in an ML context would be equivalent to iterated random search, which is essentially a zeroth-order approximation to gradient descent. Under certain simplifying assumptions, they are actually equivalent. It’s the loss landscape an parameter-function map that are responsible for most of a learning process’s inductive biases (especially for large amounts of data). See: Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent.
Most of the difference in outcomes between human biological evolution and DL comes down to the fact that bio evolution has a wildly different mapping from parameters to functional behaviors, as compared to DL. E.g.,
Bio evolution’s parameters are the genome, which mostly configures learning proclivities and reward circuitry of the human within lifetime learning process, as opposed to DL parameters being actual parameters which are much more able to directly specify particular behaviors.
The “functional output” of human bio evolution isn’t actually the behaviors of individual humans. Rather, it’s the tendency of newborn humans to learn behaviors in a given environment. It’s not like in DL, where you can train a model, then test that same model in a new environment. Rather, optimization over the human genome in the ancestral environment produced our genome, and now a fresh batch of humans arise and learn behaviors in the modern environment.
Point 2 is the distinction I was referencing when I said:
“human behavior in the ancestral environment” versus “human behavior in the modern environment” isn’t a valid example of behavioral differences between training and deployment environments.
Overall, bio evolution is an incredibly weird optimization process, with specific quirks that predictably cause very different outcomes as compared to either DL or human within lifetime learning. As a result, bio evolution outcomes have very little implication for DL. It’s deeply wrong to lump them all under the same “hill climbing paradigm”, and assume they’ll all have the same dynamics.
It’s also not necessary that the inner values of the agent make no mention of human values / objectives, it needs to both a) value them enough to not take over, and b) maintain these values post-reflection.
This ties into the misunderstanding I think you made. When I said:
The “inner loss function” I’m talking about here is not human values, but instead whatever mix of predictive loss, reward maximization, etc that form the effective optimization criterion for the brain’s “base” distributed quasi-Hebbian/whatever optimization process. Such an “inner loss function” in the context of contemporary AI systems would not refer to the “inner values” that arise as a consequence of running SGD over a bunch of training data. They’d be something much much weirder and very different from current practice.
E.g., if we had a meta-learning setup where the top-level optimizer automatically searches for a reward function F, which, when used in another AI’s training, will lead to high scores on some other criterion C, via the following process:
Randomly initializing a population of models.
Training them with the current reward function F.
Evaluate those models on C.
Update the reward function F to be better at training models to score highly on C.
The “inner loss function” I was talking about in the post would be most closely related to F. And what I mean by “Deliberately create a (very obvious[2]) inner optimizer, whose inner loss function includes no mention of human values / objectives”, in the context of the above meta-learning setup, is to point to the relationship between F and C.
Specifically, does F actually reward the AIs for doing well on C? Or, as with humans, does F only reward the AIs for achieving shallow environmental correlates of scoring well on C? If the latter, then you should obviously consider that, if you create a new batch of AIs in a fresh environment, and train them on an unmodified reward function F, that the things F rewards will become decoupled from the AIs eventually doing well on C.
Returning to humans:
Inclusive genetic fitness is incredibly difficult to “directly” train an organism to maximize. Firstly, IGF can’t actually be measured in an organism’s lifetime, only estimated based on the observable states of the organism’s descendants. Secondly, “IGF estimated from observing descendants” makes for a very difficult reward signal to learn on because it’s so extremely sparse, and because the within-lifetime actions that lead to having more descendants are often very far in time away from being able to actually observe those descendants. Thus, any scheme like “look at descendants, estimate IGF, apply reward proportional to estimated IGF” would completely fail at steering an organism’s within lifetime learning towards IGF-increasing actions.
Evolution, being faced with standard RL issues of reward sparseness and long time horizons, adopted a standard RL solution to those issues, namely reward shaping. E.g., rather than rewarding organisms for producing offspring, it builds reward circuitry that reward organisms for precursors to having offspring, such as having sex, which allows rewards to be more frequent and closer in time to the behaviors they’re supposed to reinforce.
In fact, evolution relies so heavily on reward shaping that I think there’s probably nothing in the human reward system that directly rewards increased IGF, at least not in the direct manner an ML researcher could by running a self-replicating model a bunch of times in different environments, measuring the resulting “IGF” of each run, and directly rewarding the model in proportion to its “IGF”.
This is the thing I was actually referring to when I mentioned “inner optimizer, whose inner loss function includes no mention of human values / objectives.”: the human loss / reward functions not directly including IGF in the human “base objective”.
(Note that we won’t run into similar issues with AI reward functions vs human values. This is partially because we have much more flexibility in what we include in a reward function as compared to evolution (e.g., we could directly train an AI on estimated IGF). Mostly though, it’s because the thing we want to align our models to, human values, have already been selected to be the sorts of things that can be formed via RL on shaped reward functions, because that’s how they actually arose at all.)
For (2), it seems like you are conflating ‘amount of real world time’ with ‘amount of consequences-optimization’. SGD is just a much less efficient optimizer than intelligent cognition
Again, the thing I’m pointing to as the source of the human-evolutionary sharp left turn isn’t human intelligence. It’s a change in the structure of how optimization power (coming from the “base objective” of the human brain’s updating process) was able to contribute to capabilities gains over time. If human evolution were an ML experiment, the key change I’m pointing to isn’t “the models got smart”. It’s “the experiment stopped being quite as stupidly wasteful of compute” (which happened because the models got smart enough to exploit a side-channel in the experiment’s design that allowed them to pass increasing amounts of information to future generations, rather than constantly being reset to the same level each time). Then, the reason this won’t happen in AI development is that there isn’t a similarly massive overhang of completely misused optimization power / compute, which could be unleashed via a single small change to the training process.
in-context learning happens much faster than SGD learning.
Is it really? I think they’re overall comparable ‘within an OOM’, just useful for different things. It’s just much easier to prompt a model and immediately see how this changes its behavior, but on head-to-head comparisons, it’s not at all clear that prompting wins out. E.g., Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
In particular, I think prompting tends to be more specialized to getting good performance in situations similar to those the model has seen previously, whereas training (with appropriate data) is more general in the directions in which it can move capabilities. Extreme example: pure language models can be few-shot prompted to do image classification, but are very bad at it. However, they can be directly trained into capable multi-modal models.
I think this difference between in-context vs SGD learning makes it unlikely that in-context learning alone will suffice for an explosion in general intelligence. If you’re only sampling from the probability distribution created by a training process, then you can’t update that distribution, which I expect will greatly limit your ability to robustly generalize to new domains, as compared to a process where you gather new data from those domains and update the underlying distribution with those data.
For (3), I don’t think that the SLT requires the inner optimizer to run freely, it only requires one of:
a. the inner optimizer running much faster than the outer optimizer, such that the updates don’t occur in time.
b. the inner optimizer does gradient hacking / exploration hacking, such that the outer loss’s updates are ineffective.
(3) is mostly there to point to the fact that evolution took no corrective action whatsoever in regards to humans. Evolution can’t watch humans’ within lifetime behavior, see that they’re deviating away from the “intended” behavior, and intervene in their within lifetime learning processes to correct such issues.
Human “inner learners” take ~billions of inner steps for each outer evolutionary step. In contrast, we can just assign whatever ratio of supervisory steps to runtime execution steps, and intervene whenever we want.
It doesn’t mention the literal string “gradient descent”, but it clearly makes reference to the current methodology of training AI systems (which is gradient descent). E.g., here:
The techniques OpenMind used to train it away from the error where it convinces itself that bad situations are unlikely? Those generalize fine. The techniques you used to train it to allow the operators to shut it down? Those fall apart, and the AGI starts wanting to avoid shutdown, including wanting to deceive you if it’s useful to do so.
The implication is that the dangerous behaviors that manifest during the SLT are supposed to have been instilled (at least partially) during the training (gradient descent) process.
However, the above is a nitpick. The real issue I have with your comment is that you seem to be criticizing me for not addressing the “capabilities come from not-SGD” threat scenario, when addressing that threat scenario is what this entire post is about.
Here’s how I described SLT (which you literally quoted): “SGD creating some ‘inner thing’ which is not SGD and which gains capabilities much faster than SGD can insert them into the AI.”
This is clearly pointing to a risk scenario where something other than SGD produces the SLT explosion of capabilities.
You say:
For example, Auto-GPT is composed of foundation models which were trained with SGD and RHLF, but there are many ways to enhance the capabilities of Auto-GPT that do not involve further training of the foundation models. The repository currently has hundreds of open issues and pull requests. Perhaps a future instantiation of Auto-GPT will be able to start closing these PRs on its own, but in the meantime there are plenty of humans doing that work.
To which I say, yes, that’s an example where SGD creates some ‘inner thing’ (the ability to contribute to the Auto-GPT repository), which (one might imagine) would let Auto-GPT “gain capabilities much faster than SGD can insert them into the AI.” This is exactly the sort of thing that I’m talking about in this post, and am saying it won’t lead to an SLT.
(Or at least, that the evolutionary example provides no reason to think that Auto-GPT might undergo an SLT, because the evolutionary SLT relied on the sudden unleash of ~9 OOM extra available optimization power, relative to the previous mechanisms of capabilities accumulation over time.)
Finally, I’d note that a very significant portion of this post is explicitly focused on discussing “non-SGD” mechanisms of capabilities improvement. Everything from “Fast takeoff is still possible” and on is specifically about such scenarios.
I’ve recently decided to revisit this post. I’ll try to address all un-responded to comments in the next ~2 weeks.
Part of this is just straight disagreement, I think; see So8res’s Sharp Left Turn and follow-on discussion.
Evolution provides no evidence for the sharp left turn
But for the rest of it, I don’t see this as addressing the case for pessimism, which is not problems from the reference class that contains “the LLM sometimes outputs naughty sentences” but instead problems from the reference class that contains “we don’t know how to prevent an ontological collapse, where meaning structures constructed under one world-model compile to something different under a different world model.”
I dislike this minimization of contemporary alignment progress. Even just limiting ourselves to RLHF, that method addresses far more problems than “the LLM sometimes outputs naughty sentences”. E.g., it also tackles problems such as consistently following user instructions, reducing hallucinations, improving the topicality of LLM suggestions, etc. It allows much more significant interfacing with the cognition and objectives pursued by LLMs than just some profanity filter.
I don’t think ontological collapse is a real issue (or at least, not an issue that appropriate training data can’t solve in a relatively straightforwards way). I feel similarly about lots of things that are speculated to be convergent problems for ML systems, such as wireheading and mesaoptimization.
Or, like, once LLMs gain the capability to design proteins (because you added in a relevant dataset, say), do you really expect the ‘helpful, harmless, honest’ alignment techniques that were used to make a chatbot not accidentally offend users to also work for making a biologist-bot not accidentally murder patients?
If you’re referring to the technique used on LLMs (RLHF), then the answer seems like an obvious yes. RLHF just refers to using reinforcement learning with supervisory signals from a preference model. It’s an incredibly powerful and flexible approach, one that’s only marginally less general than reinforcement learning itself (can’t use it for things you can’t build a preference model of). It seems clear enough to me that you could do RLHF over the biologist-bot’s action outputs in the biological domain, and be able to shape its behavior there.
If you’re referring to just doing language-only RLHF on the model, then making a bio-model, and seeing if the RLHF influences the bio-model’s behaviors, then I think the answer is “variable, and it depends a lot on the specifics of the RLHF and how the cross-modal grounding works”.
People often translate non-lingual modalities into language so LLMs can operate in their “native element” in those other domains. Assuming you don’t do that, then yes, I could easily see the language-only RLHF training having little impact on the bio-model’s behaviors.
However, if the bio-model were acting multi-modally by e.g., alternating between biological sequence outputs and natural language planning of what to use those outputs for, then I expect the RLHF would constrain the language portions of that dialog. Then, there are two options:
Bio-bot’s multi-modal outputs don’t correctly ground between language and bio-sequences.
In this case, bio-bot’s language planning doesn’t correctly describe the sequences its outputting, so the RLHF doesn’t constrain those sequences.
However, if bio-bot doesn’t ground cross-modally, than bio-bot also can’t benefit from its ability to plan in the language modality to better use its bio modality capabilities (which are presumably much better for planning than its bio-modality).
Bio-bot’s multi-modal outputs DO correctly ground between language and bio-sequences.
In that case, the RLHF-constrained language does correctly describe the bio-sequences, and so the language-only RLHF training does also constrain bio-bot’s biology-related behavior.
Put another way, I think new capabilities advances reveal new alignment challenges and unless alignment techniques are clearly cutting at the root of the problem, I don’t expect that they will easily transfer to those new challenges.
Whereas I see future alignment challenges as intimately tied to those we’ve had to tackle for previous, less capable models. E.g., your bio-bot example is basically a problem of cross-modality grounding, on which there has been an enormous amount of past work, driven by the fact that cross-modality grounding is a problem for systems across very broad ranges of capabilities.
There was an entire thread about Yudkowsky’s past opinions on neural networks, and I agree with Alex Turner’s evidence that Yudkowsky was dubious.
I also think people who used brain analogies as the basis for optimism about neural networks were right to do so.
Roughly, the core distinction between software engineering and computer security is whether the system is thinking back.
Yes, and my point in that section is that the fundamental laws governing how AI training processes work are not “thinking back”. They’re not adversaries. If you created a misaligned AI, then it would be “thinking back”, and you’d be in an adversarial position where security mindset is appropriate.
What’s your story for specification gaming?
“Building an AI that doesn’t game your specifications” is the actual “alignment question” we should be doing research on. The mathematical principles which determine how much a given AI training process games your specifications are not adversaries. It’s also a problem we’ve made enormous progress on, mostly by using large pretrained models with priors over how to appropriately generalize from limited specification signals. E.g., Learning Which Features Matter: RoBERTa Acquires a Preference for Linguistic Generalizations (Eventually) shows how the process of pretraining an LM causes it to go from “gaming” a limited set of finetuning data via shortcut learning / memorization, to generalizing with the appropriate linguistic prior knowledge.
It can be induced on MNIST by deliberately choosing worse initializations for the model, as Omnigrok demonstrated.
Re empirical evidence for influence functions:
Didn’t the Anthropic influence functions work pick up on LLMs not generalising across lexical ordering? E.g., training on “A is B” doesn’t raise the model’s credence in “Bs include A”?
Which is apparently true: https://x.com/owainevans_uk/status/1705285631520407821?s=46
I think you’re missing something regarding David’s contribution:
Yes, this reasoning was for capabilities benchmarks specifically. Data goes further with future algorithmic progress, so I thought a narrower criteria for that one was reasonable.
So, you are deliberately targeting models such as LLama-2, then? Searching HuggingFace for “Llama-2” currently brings up 3276 models. As I understand the legislation you’re proposing, each of these models would have to undergo government review, and the government would have the perpetual capacity to arbitrarily pull the plug on any of them.
I expect future small, open-source models to prioritize runtime efficiency, and so will over-train as much as possible. As a result, I expect that most of the open source ecosystem will be using models trained on > 1 T tokens. I think StableDiffusion is within an OOM of the 1 T token cutoff, since it was trained on a 2 billion image/text pairs subset of the LAION-5B dataset, and judging from the sample images on page 35, the captions are a bit less than 20 tokens per image. Future open source text-to-image models will likely be trained with > 1 T text tokens. Once that happens, the hobbyist and individual creators responsible for the vast majority of checkpoints / LORAs on model sharing sites like Civitai will also be subject to these regulations.
I expect language / image models will increasingly become the medium through which people express themselves, the next internet, so to speak. I think that giving the government expansive powers of censorship over the vast majority[1] of this ecosystem is extremely bad, especially for models that we know are not a risk.
I also think it is misleading for you to say things like:
and:
but then propose rules that would actually target a very wide (and increasing) swath of open-source, academic, and hobbyist work.
- ^
Weighted by what models people of the future actually use / interact with.
- ^
What about RLHF’d GPT-4?
Your current threshold does include all Llama models (other than llama-1 6.7/13 B sizes), since they were trained with > 1 trillion tokens.
I also think 70% on MMLU is extremely low, since that’s about the level of ChatGPT 3.5, and that system is very far from posing a risk of catastrophe.
The cutoffs also don’t differentiate between sparse and dense models, so there’s a fair bit of non-SOTA-pushing academic / corporate work that would fall under these cutoffs.
Out of curiosity, I skimmed the Ted Gioia linked article and encountered this absolutely wild sentence:
AI is getting more sycophantic and willing to agree with false statements over time.
which is just such a complete misunderstanding of the results from Discovering Language Model Behaviors with Model-Written Evaluations. Instantly disqualified the author from being someone I’d pay attention to for AI-related analysis.
Perhaps, but that’s not the literal meaning of the text.
Here’s what we now know about AI:
[...]
AI potentially creates a situation where millions of people can be fired and replaced with bots [...]
It is legal, in the US at least. See: https://en.wikipedia.org/wiki/The_Anarchist_Cookbook#Reception